{"id":"https://openalex.org/W2250612599","doi":"https://doi.org/10.3115/v1/w14-3360","title":"An Empirical Comparison of Features and Tuning for Phrase-based Machine Translation","display_name":"An Empirical Comparison of Features and Tuning for Phrase-based Machine Translation","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2250612599","doi":"https://doi.org/10.3115/v1/w14-3360","mag":"2250612599"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-3360","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3360","pdf_url":"https://aclanthology.org/W14-3360.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth Workshop on Statistical Machine Translation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-3360.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004988074","display_name":"Spence Green","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Spence Green","raw_affiliation_strings":["Computer Science Department, Stanford University"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073726152","display_name":"Daniel Cer","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Cer","raw_affiliation_strings":["Computer Science Department, Stanford University"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046006076","display_name":"Christopher D. Manning","orcid":"https://orcid.org/0000-0001-6155-649X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Manning","raw_affiliation_strings":["Computer Science Department, Stanford University"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004988074"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":6.3426,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.96597972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"466","last_page":"476"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.9384645223617554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8128924369812012},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.783297061920166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7227957248687744},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7001961469650269},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6846263408660889},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6767054200172424},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6207868456840515},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5258379578590393},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5145744681358337},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48841947317123413},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40093833208084106},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3380555510520935},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.06981027126312256}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9384645223617554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8128924369812012},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.783297061920166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7227957248687744},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7001961469650269},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6846263408660889},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6767054200172424},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6207868456840515},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5258379578590393},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5145744681358337},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48841947317123413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40093833208084106},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3380555510520935},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.06981027126312256},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/w14-3360","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3360","pdf_url":"https://aclanthology.org/W14-3360.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth Workshop on Statistical Machine Translation","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.570.4900","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.570.4900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.spencegreen.com/pubs/green+cer+manning.features.wmt14.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.676.2932","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.676.2932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/W/W14/W14-3360.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-3360","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3360","pdf_url":"https://aclanthology.org/W14-3360.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth Workshop on Statistical Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7699999809265137,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G6894402473","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250612599.pdf","grobid_xml":"https://content.openalex.org/works/W2250612599.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W91928571","https://openalex.org/W232191560","https://openalex.org/W298172948","https://openalex.org/W1498269992","https://openalex.org/W1502599399","https://openalex.org/W1565703351","https://openalex.org/W1595109586","https://openalex.org/W1632114991","https://openalex.org/W1901440691","https://openalex.org/W2096204319","https://openalex.org/W2100631779","https://openalex.org/W2101105183","https://openalex.org/W2101451733","https://openalex.org/W2104936489","https://openalex.org/W2105891181","https://openalex.org/W2107564089","https://openalex.org/W2108622839","https://openalex.org/W2110168585","https://openalex.org/W2110898493","https://openalex.org/W2112544287","https://openalex.org/W2115259925","https://openalex.org/W2118692229","https://openalex.org/W2119168550","https://openalex.org/W2119706326","https://openalex.org/W2120354757","https://openalex.org/W2123318312","https://openalex.org/W2124807415","https://openalex.org/W2125595887","https://openalex.org/W2131988669","https://openalex.org/W2135573497","https://openalex.org/W2140343992","https://openalex.org/W2141440284","https://openalex.org/W2142112143","https://openalex.org/W2143564602","https://openalex.org/W2146502635","https://openalex.org/W2146574666","https://openalex.org/W2153653739","https://openalex.org/W2156985047","https://openalex.org/W2158049734","https://openalex.org/W2159755860","https://openalex.org/W2164301055","https://openalex.org/W2169724380","https://openalex.org/W2171421863","https://openalex.org/W2180952760","https://openalex.org/W2183072638","https://openalex.org/W2185701500","https://openalex.org/W2250659129","https://openalex.org/W2250907725","https://openalex.org/W2250947781","https://openalex.org/W2251912507","https://openalex.org/W2252102852","https://openalex.org/W2293596968","https://openalex.org/W2340221426","https://openalex.org/W2595715041","https://openalex.org/W2620723628","https://openalex.org/W3012264151","https://openalex.org/W3146885639","https://openalex.org/W4241645538","https://openalex.org/W6605321254","https://openalex.org/W6743119038"],"related_works":["https://openalex.org/W3040691452","https://openalex.org/W2384400852","https://openalex.org/W3204898214","https://openalex.org/W2963259630","https://openalex.org/W4240926580","https://openalex.org/W2070920720","https://openalex.org/W2475062008","https://openalex.org/W2883671469","https://openalex.org/W2122294272","https://openalex.org/W2398549619"],"abstract_inverted_index":{"Scalable":[0],"discriminative":[1],"training":[2],"methods":[3],"are":[4,24,57],"now":[5],"broadly":[6],"available":[7],"for":[8,80,120],"estimating":[9],"phrase-based,":[10],"feature-rich":[11,91],"translation":[12,35],"models.":[13],"However,":[14],"the":[15,96,122],"sparse":[16,68],"feature":[17,49,97],"sets":[18],"typically":[19],"appearing":[20],"in":[21],"research":[22],"evaluations":[23],"less":[25,109],"attractive":[26],"than":[27,60,66],"standard":[28],"dense":[29,61],"features":[30,62,75],"such":[31],"as":[32],"language":[33],"and":[34,47,84,113,117],"model":[36],"probabilities:":[37],"they":[38],"often":[39],"overfit,":[40],"do":[41],"not":[42],"generalize,":[43],"or":[44],"require":[45],"complex":[46],"slow":[48],"extractors.":[50],"This":[51],"paper":[52],"introduces":[53],"extended":[54,74],"features,":[55],"which":[56],"more":[58,64],"specific":[59,100],"yet":[63],"general":[65],"lexicalized":[67],"features.":[69,123],"Large-scale":[70],"experiments":[71],"show":[72],"that":[73,107],"yield":[76],"robust":[77],"BLEU":[78],"gains":[79],"both":[81],"Arabic-English":[82],"(+1.05)":[83],"Chinese-English":[85],"(+0.67)":[86],"relative":[87],"to":[88,99,111],"a":[89],"strong":[90],"baseline.":[92],"We":[93],"also":[94],"specialize":[95],"set":[98],"data":[101],"domains,":[102],"identify":[103],"an":[104],"objective":[105],"function":[106],"is":[108],"prone":[110],"overfitting,":[112],"release":[114],"fast,":[115],"scalable,":[116],"language-independent":[118],"tools":[119],"implementing":[121]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}